A comparison of some new and old robust ridge regression estimators

被引:24
|
作者
Ali, Sajid [1 ]
Khan, Himmad [2 ]
Shah, Ismail [1 ]
Butt, Muhammad Moeen [3 ]
Suhail, Muhammad [4 ,5 ]
机构
[1] Quaid I Azam Univ, Dept Stat, Islamabad 45320, Pakistan
[2] Govt Higher Secondary Sch Aboha, Swat, Pakistan
[3] Univ Management & Technol, Sch Business & Econ, Dept Quantitat Methods, Lahore, Pakistan
[4] Univ Punjab, Coll Stat & Actuarial Sci, Lahore, Pakistan
[5] Univ Agr, Dept Stat Math & Comp Sci, Peshawar, Khyber Pakhtunk, Pakistan
关键词
Multicollinearity; Ridge regression; Monte Carlo Simulation; BIASED ESTIMATION; SIMULATION;
D O I
10.1080/03610918.2019.1597119
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Ridge regression is used to circumvent the problem of multicollinearity among predictors and many estimators for ridge parameter are available in the literature. However, if the level of collinearity among predictors is high, the existing estimators also have high mean square errors (MSE). In this paper, we consider some existing and propose new estimators for the estimation of ridge parameter k. Extensive Monte Carlo simulations as well as a real-life example are used to evaluate the performance of proposed estimators based on the MSE criterion. The results show the superiority of our proposed estimators compared to the existing estimators.
引用
收藏
页码:2213 / 2231
页数:19
相关论文
共 50 条
  • [21] ROBUST RIDGE ESTIMATORS
    DEWET, AG
    DEWET, T
    SOUTH AFRICAN STATISTICAL JOURNAL, 1984, 18 (02) : 183 - 183
  • [22] Robust regression estimators: A comparison of prediction performance
    Kalina, Jan
    Pestova, Barbora
    MATHEMATICAL METHODS IN ECONOMICS (MME 2017), 2017, : 307 - 312
  • [23] SOME THEORETICAL RESULTS FOR GENERALIZED RIDGE-REGRESSION ESTIMATORS
    FOURGEAUD, C
    GOURIEROUX, C
    PRADEL, J
    JOURNAL OF ECONOMETRICS, 1984, 25 (1-2) : 191 - 203
  • [24] Performance of some ridge regression estimators for the multinomial logit model
    Mansson, Kristofer
    Shukur, Ghazi
    Kibria, B. M. Golam
    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2018, 47 (12) : 2795 - 2804
  • [25] On some beta ridge regression estimators: method, simulation and application
    Qasim, Muhammad
    Mansson, Kristofer
    Golam Kibria, B. M.
    JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 2021, 91 (09) : 1699 - 1712
  • [26] A note on some new modifications of ridge estimators
    Asar, Yasin
    Genc, Asir
    KUWAIT JOURNAL OF SCIENCE, 2017, 44 (03) : 75 - 82
  • [27] Modified Ridge Regression Estimators
    Khalaf, G.
    Mansson, Kristofer
    Shukur, Ghazi
    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2013, 42 (08) : 1476 - 1487
  • [28] Modified Robust Ridge M-Estimators in Two-Parameter Ridge Regression Model
    Yasin, Seyab
    Salem, Sultan
    Ayed, Hamdi
    Kamal, Shahid
    Suhail, Muhammad
    Khan, Yousaf Ali
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2021, 2021
  • [29] New ridge parameter estimators for the quasi-Poisson ridge regression model
    Shahzad, Aamir
    Amin, Muhammad
    Emam, Walid
    Faisal, Muhammad
    SCIENTIFIC REPORTS, 2024, 14 (01)
  • [30] SOME NEW ESTIMATORS FOR COX REGRESSION
    SASIENI, P
    ANNALS OF STATISTICS, 1993, 21 (04): : 1721 - 1759